Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 254 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0645. Min Range: -4.0645

Max Act: 4.0645. Min Act: -0.1700

Data Index: 6100746 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.0645. Min Range: -4.0645

Max Act: 4.0519. Min Act: -0.1700

Data Index: 6174594 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 4.0645. Min Range: -4.0645

Max Act: 4.0417. Min Act: -0.1700

Data Index: 1880142 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.9854. Min Act: -0.1700

Data Index: 6743579 (Open Web Text)

Max Activating Token Index: 733

Text #4

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.9212. Min Act: -0.1700

Data Index: 1546093 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8943. Min Act: -0.1700

Data Index: 5409152 (Open Web Text)

Max Activating Token Index: 107

Text #6

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8876. Min Act: -0.1700

Data Index: 1880090 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8844. Min Act: -0.1700

Data Index: 5117429 (Open Web Text)

Max Activating Token Index: 228

Text #8

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8722. Min Act: -0.1700

Data Index: 7434443 (Open Web Text)

Max Activating Token Index: 187

Text #9

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8904. Min Act: -0.1700

Data Index: 1996754 (Open Web Text)

Max Activating Token Index: 688

Text #10

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8866. Min Act: -0.1700

Data Index: 1995974 (Open Web Text)

Max Activating Token Index: 542

Text #11

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8746. Min Act: -0.1700

Data Index: 4261918 (Open Web Text)

Max Activating Token Index: 321

Text #12

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8567. Min Act: -0.1700

Data Index: 5243130 (Open Web Text)

Max Activating Token Index: 449

Text #13

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8202. Min Act: -0.1700

Data Index: 2876081 (Open Web Text)

Max Activating Token Index: 922

Text #14

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8386. Min Act: -0.1700

Data Index: 7700384 (Open Web Text)

Max Activating Token Index: 819

Text #15

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8138. Min Act: -0.1700

Data Index: 1995975 (Open Web Text)

Max Activating Token Index: 75

Text #16

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8286. Min Act: -0.1700

Data Index: 1825749 (Open Web Text)

Max Activating Token Index: 493

Text #17

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8319. Min Act: -0.1700

Data Index: 3582652 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.7851. Min Act: -0.1700

Data Index: 4347178 (Open Web Text)

Max Activating Token Index: 149

Text #19

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8072. Min Act: -0.1700

Data Index: 5202087 (Open Web Text)

Max Activating Token Index: 822